OpenAI Progress

Re:OpenAI Progress by gordon_freeman on Saturday August 16, 2025 @07:17PM (#44927643)

It seems like the progress from GPT-4 to GPT-5 has plateaued: for most prompts, I actually find GPT-4 more understandable than GPT-5 [1].

[1] Read the answers from GPT-4 and 5 for this math question: "Ugh I hate math, integration by parts doesn't make any sense"

[ Parent | on HN ]

Re:OpenAI Progress by energy123 on Saturday August 16, 2025 @10:34PM (#44928446)

Basic prose is a saturated bench. You can't go above 100% so by definition progress will stall on such benchmarks.

[ Parent | on HN ]

Re:OpenAI Progress by RugnirViking on Sunday August 17, 2025 @04:27AM (#44929914)

You say that, but I can imagine a good maths textbook and a bad one, both technically correct and well written prose, but one is better at taking the student on a journey and understanding where people fall off and common misunderstandings without odiously re-explaining everything

[ Parent | on HN ]